uttapen

Magnum v4 72B vs Claude Haiku 4.5

Both sit behind the same key and the same code on uttapen — the only thing that changes is the model string, so you can run each of them against your own workload without touching anything else. On cost, Claude Haiku 4.5 comes out about 1.3× cheaper.

FeatureMagnum v4 72BClaude Haiku 4.5
ProviderAnthracite OrgAnthropic
Model idanthracite-org/magnum-v4-72banthropic/claude-haiku-4.5
Context32,768 tokens200,000 tokens
Max output4,096 tokens64,000 tokens
Input / 1M tokens725,313 toman290,125 toman
Output / 1M tokens1,450,625 toman1,450,625 toman
≈ one 1,000-word request2,829 toman2,263 toman
Input cachingNo29,013 toman / 1M
Image inputNoYes
File inputNoYes
Tool callingNoYes
JSON outputYesYes
Reasoning modeNoYes

Which one for what?

Magnum v4 72B

  • Chat, summarising, and everyday text generation
2,829 toman per 1,000 words · Model page

Claude Haiku 4.5

  • Multi-step problems, maths, and tracking down a bug
  • Whole documents or a codebase in a single request
  • Reading screenshots, invoices, and scanned forms
  • Agents that call your own APIs and database
2,263 toman per 1,000 words · Model page

Run both with the same code

Swap the model value between the two ids and send the same request twice; what each answer cost comes back in the X-Uttapen-Cost-Toman header.

curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthracite-org/magnum-v4-72b",
    "messages": [{"role": "user", "content": "Introduce yourself in one sentence."}],
    "stream": true
  }'

model = "anthropic/claude-haiku-4.5"

More comparisons: all pairs · model rankings · full catalogue

base_url = https://api.uttapen.ir/v1